Convolutional Neural Network Object Detection Algorithm for Identifying Species of Panthera

Panthera is a genus in the Felidae (cat) family that includes three well-known species: i) tigers, ii) lions, and iii) jaguars. This genus is also known as 'big cats'. Panthera is also considered the most dangerous and extinct animal. It is very important to protect the Panthera species. H...

Full description

Bibliographic Details
Published in:2023 IEEE Symposium on Industrial Electronics and Applications, ISIEA 2023
Main Author: Akmal Yazid M.N.; Zainal Abidin N.A.; Aminuddin R.; Mohamed Ibrahim A.Z.; Ibrahim Teo N.H.; Nabilah Mohd Nasir S.D.; Hamzah R.; Fariza Abu Samah K.A.
Format: Conference paper
Language:English
Published: Institute of Electrical and Electronics Engineers Inc. 2023
Online Access:https://www.scopus.com/inward/record.uri?eid=2-s2.0-85170086187&doi=10.1109%2fISIEA58478.2023.10212137&partnerID=40&md5=97f6f042a302e460e6ffca0ce8ad5c89
Description
Summary:Panthera is a genus in the Felidae (cat) family that includes three well-known species: i) tigers, ii) lions, and iii) jaguars. This genus is also known as 'big cats'. Panthera is also considered the most dangerous and extinct animal. It is very important to protect the Panthera species. However, it is challenging to identify the species as they share some similarities in characteristics such as the shape of the face, size, etc. Therefore, an artificial intelligence approach is used to solve this problem. The goals of this project are to design and develop a system that can detect three Panthera species automatically: 1) tiger, 2) lion, and 3) jaguar. The system is developed with a Convolutional Neural Network algorithm and the methodology of the project is using the Waterfall model. There are four phases in the Waterfall model i) requirement analysis, ii) system design, iii) implementation, and iv) testing. The results show that the deep learning model can achieve accuracy of 100% in the training set and 93.33% in the testing set. © 2023 IEEE.
ISSN:
DOI:10.1109/ISIEA58478.2023.10212137